DIAGNOSIS ABNORMALITAS KONTROL SUHU HEAT EXCHANGER INDUSTRI PETROKIMIA BERBASIS CERTAINTY FACTOR
DOI:
https://doi.org/10.53026/prosidingsntem.v5i1.585Keywords:
sistem pakar, certainty factor, heat exchanger, diagnosis abnormalitas, industri petrokimiaAbstract
Heat exchanger merupakan komponen krusial dalam industri petrokimia yang rentan mengalami abnormalitas kontrol suhu akibat fouling, malfungsi control valve, drift sensor, dan gangguan lainnya. Deteksi dini abnormalitas masih menghadapi tantangan signifikan karena ketergantungan pada pengalaman operator, alarm flood, serta potensi human error. Penelitian ini mengembangkan sistem pakar berbasis Certainty Factor (CF) untuk mendiagnosis abnormalitas kontrol suhu heat exchanger di industri petrokimia. Knowledge base dibangun melalui observasi lapangan bersama pakar, menghasilkan dataset komprehensif dengan 314 gejala dan 32 jenis kerusakan. Sistem diimplementasikan menggunakan Python dengan antarmuka web yang memungkinkan operator memilih gejala, kemudian sistem menghitung nilai CF dan memberikan diagnosis beserta rekomendasi perbaikan. Evaluasi terhadap 22 skenario menunjukkan akurasi 81,82%, precision 100%, recall 81,82%, dan F1-score 90,00%. Nilai CF rata-rata 90,32% dengan perbedaan signifikan antara diagnosis benar (94,43%) dan salah (72,00%), membuktikan efektivitas CF sebagai indikator ketidakpastian. Precision 100% mengindikasikan tidak ada false positive, penting untuk menghindari tindakan perbaikan tidak perlu di lingkungan petrokimia berisiko tinggi. Sistem ini berfungsi sebagai decision support tool yang dapat diimplementasikan tanpa infrastruktur tambahan untuk pengambilan keputusan yang lebih cepat, akurat, dan konsisten.
References
F. Deng and F. Wang, “Misoperation monitoring and early warning during startup and shutdown of petrochemical units,” J. Loss Prev. Process Ind., vol. 67, p. 104265, 2020, doi: 10.1016/j.jlp.2020.104265.
A. Elwerfalli, S. Alsadaie, and I. M. Mujtaba, “Estimation of shutdown schedule to remove fouling layers of heat exchangers using risk-based inspection (RBI),” Processes, vol. 9, no. 12, p. 2177, 2021, doi: 10.3390/pr9122177.
W. Augustin, L. F. Melo, and D. I. Wilson, “Towards a common taxonomy for heat exchanger fouling,” in Heat Exchanger Fouling and Cleaning XV – 2024, Heat Transfer (HMT), 2025.
B. Pfortner, W. Al Hadad, V. Schick, et al., “Transient detection of either maldistribution or flowrate change in a counter current plate-fin heat exchanger using an ARX model,” Chem. Eng. Res. Des., vol. 163, pp. 325–335, 2021, doi: 10.1016/j.cherd.2020.12.031.
T. S. Purwanto, D. I. Permana, M. Nurbanasari, et al., “Failure analysis of low- pressure evaporator in heat recovery steam generator with 200 ton/h of capacity,” J. Fail. Anal. Prev., vol. 23, no. 5, p. 01769, 2023, doi: 10.1007/s11668-023-01769-7.
K. Parsa, M. Hassall, and M. Naderpour, “Enhancing Alarm Prioritization in the Alarm Management Lifecycle,” IEEE Access, vol. 10, pp. 99–111, 2021, doi: 10.1109/ACCESS.2021.3137865.
A. Misuri, G. Landucci, and V. Cozzani, “Assessment of safety barrier performance in the mitigation of domino scenarios caused by Natech events,” Reliab. Eng. Syst. Saf., vol. 205, p. 107278, 2021, doi: 10.1016/j.ress.2020.107278.
J. Zhang, W. Luo, and Y. Dai, “Integrated diagnostic framework for process and sensor faults in chemical industry,” Sensors, vol. 21, no. 3, p. 822, 2021, doi: 10.3390/s21030822.
M. Golyadkin, V. Pozdnyakov, L. Zhukov, and I. Makarov, “SensorSCAN: Self- supervised learning and deep clustering for fault diagnosis in chemical processes,” Artif. Intell., vol. 324, p. 104012, 2023, doi: 10.1016/j.artint.2023.104012.
W. Li, H. Li, S. Gu, et al., “Process fault diagnosis with model- and knowledge- based approaches: Advances and opportunities,” J. Process Control, vol. 80, pp. 35–45, 2020, doi: 10.1016/j.jprocont.2020.02.003.
D. Bouhalouan, B. Nachet, and A. Adla, “Knowledge-Intensive Decision Support System for Manufacturing Equipment Maintenance,” J. Decis. Syst., vol. 18, no. 3, pp. 85–98, 2020, doi: 10.6025/jdim/2020/18/3/85-98.
G. R. Taira, S. W. Park, and A. C. Zanin, “Fault detection in a fluid catalytic cracking process using a Bayesian recurrent neural network,” in Proc. 13th IFAC Symp. on Dynamics and Control of Process Systems, Including Biosystems (DYCOPS 2022), 2022, pp. 1–6.
W. Yan, J. Wang, S. Lu, et al., “A review of real-time fault diagnosis methods for industrial smart manufacturing,” Processes, vol. 11, p. 369, 2023, doi: 10.3390/pr11020369.
Reetz, T. Neumann, G. Schrijver, et al., “Expert system-based fault diagnosis for railway point machines,” J. Rail Transp. Plann. Manage., vol. 15, pp. 50–60, 2023, doi: 10.1016/j.jrtpm.2022.100074.
X. Yuan et al., “A comparative analysis of certainty factor-based machine learning methods for collapse and landslide susceptibility mapping in Wenchuan County, China,” Remote Sens (Basel), vol. 14, no. 14, p. 3259, 2022, doi: 10.3390/rs14143259.
R. Irsyada, N. Cahyani, and L. Badriyah, “Innovation of an expert system for diagnosing allergic diseases in children using the web-based certainty factor method,” Brilliance: Research of Artificial Intelligence, vol. 4, no. 2, pp. 909–918, 2024.
A. Kusnadi, Y. Arkeman, K. Syamsu, and S. H. Wijaya, “Certainty factor-based expert system for meat classification within an enterprise resource planning framework,” Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, vol. 9, no. 3, pp. 661–672, 2023.
K. E. Setyaputri, A. Fadlil, and Sunardi, “Comparative analysis of certainty factor method and Bayes probability method on ENT disease expert system,” Scientific Journal of Informatics, vol. 5, no. 2, pp. 142–150, 2018.
Downloads
Published
Conference Proceedings Volume
Section
License
Copyright (c) 2025 Prosiding Seminar Nasional Teknologi Energi dan Mineral
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
